depend on the previous behavior, you can explicitly set the Agent's `InferenceDevice` to `InferenceDevice.CPU`. (#5175)
- Added support for `Goal Signal` as a type of observation. Trainers can now use HyperNetworks to process `Goal Signal`. Trainers with HyperNetworks are more effective at solving multiple tasks. (#5142, #5159, #5149)
- Modified the [GridWorld environment](https://github.com/Unity-Technologies/ml-agents/blob/main/docs/Learning-Environment-Examples.md#gridworld) to use the new `Goal Signal` feature. (#5193)
- `DecisionRequester.ShouldRequestDecision()` and `ShouldRequestAction()`methods were added. These are used to
determine whether `Agent.RequestDecision()` and `Agent.RequestAction()` are called (respectively). (#5223)
- `RaycastPerceptionSensor` now caches its raycast results; they can be accessed via `RayPerceptionSensor.RayPerceptionOutput`. (#5222)